Mining Fuzzy Frequent Item Sets
نویسندگان
چکیده
Due to various reasons transaction data often lack information about some items. This leads to the problem that some potentially interesting frequent item sets cannot be discovered, since by exact matching the number of supporting transactions may be smaller than the user-specified minimum. In this study we try to find such frequent item sets nevertheless by inserting missing items into transactions during the mining process in order to allow approximate matching. We present a recursive elimination algorithm, based on a step by step elimination of items from the transaction database together with a recursive processing of transaction subsets. This algorithm is very simple, works without complicated data structures, and allows us to find fuzzy frequent item sets easily.
منابع مشابه
An Efficient Algorithm for Mining Fuzzy Temporal Data
Mining patterns from fuzzy temporal data is an important data mining problem. One of these mining task is to find locally frequent sets, In most of the earlier works fuzziness was considered in the time attribute of the datasets .Although a couple of works have been done in dealing with such data, little has been done on the implementation side. In this article, we propose an efficient implemen...
متن کاملA Fuzzy Algorithm for Mining High Utility Rare Itemsets – FHURI
Classical frequent itemset mining identifies frequent itemsets in transaction databases using only frequency of item occurrences, without considering utility of items. In many real world situations, utility of itemsets are based upon user’s perspective such as cost, profit or revenue and are of significant importance. Utility mining considers using utility factors in data mining tasks. Utility-...
متن کاملFuzzy Frequent Item Set Mining based on Recursive Elimination
Real life transaction data often miss some occurrences of items that are actually present. As a consequence some potentially interesting frequent item sets cannot be discovered, since with exact matching the number of supporting transactions may be smaller than the user-specified minimum. In order to allow approximate matching during the mining process, we propose an approach based on transacti...
متن کاملSaM: A Split and Merge Algorithm for Fuzzy Frequent Item Set Mining
This paper presents SaM, a split and merge algorithm for frequent item set mining. Its distinguishing qualities are an exceptionally simple algorithm and data structure, which not only render it easy to implement, but also convenient to execute on external storage. Furthermore, it can easily be extended to allow for “fuzzy” frequent item set mining in the sense that missing items can be inserte...
متن کاملA Novel Approach for finding Frequent Item Sets with Hybrid Strategies
Frequent item sets mining plays an important role in association rules mining. Over the years, a variety of algorithms for finding frequent item sets in very large transaction databases have been developed. Therefore, a number of methods have been proposed recently to discover approximate frequent item sets. This paper proposes an efficient SMine (Sorted Mine) Algorithm for finding frequent ite...
متن کامل